Approach to Improve the Performance Using Bit-level Sparsity in Neural Networks
- Title
- Approach to Improve the Performance Using Bit-level Sparsity in Neural Networks
- Authors
- Kang, Yesung; Kwon, Eunji; Lee, Seunggyu; Byun, Younghoon; Lee, Youngjoo; Kang, Seokhyeong
- Date Issued
- 2021-02-02
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Abstract
- This paper presents a convolutional neural network (CNN) accelerator that can skip zero weights and handle outliers, which are few but have a significant impact on the accuracy of CNNs, to achieve speedup and increase the energy efficiency of CNN. We propose an offline weight-scheduling algorithm which can skip zero weights and combine two non-outlier weights simultaneously using bit-level sparsity of CNNs. We use a reconfigurable multiplier-and-accumulator (MAC) unit for two purposes; usually used to compute combined two non-outliers and sometimes to compute outliers. We further improve the speedup of our accelerator by clipping some of the outliers with negligible accuracy loss. Compared to DaDianNao [7] and Bit-Tactical [16] architectures, our CNN accelerator can improve the speed by 3.34 and 2.31 times higher and reduce energy consumption by 29.3% and 30.2%, respectively.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/109924
- Article Type
- Conference
- Citation
- 2021 Design, Automation and Test in Europe Conference and Exhibition, DATE 2021, page. 1516 - 1521, 2021-02-02
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.